© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93078
    Prev
    Next
    INDEX
    Explanations

    statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     figure
    -1.77
    figure
    -1.24
     figured
    -1.23
     figuring
    -1.14
     realize
    -0.93
     mean
    -0.91
     figura
    -0.90
    figured
    -0.90
     determine
    -0.81
     Figure
    -0.74
    POSITIVE LOGITS
    RegressionTest
    0.79
    OGND
    0.69
    зулта
    0.64
    heads
    0.63
    thâu
    0.60
    kháu
    0.59
    createCanvas
    0.58
    KURZBESCHREIBUNG
    0.55
    Geplaatst
    0.54
    boards
    0.54
    Activations Density 0.065%

    No Known Activations